INDEX

Explanations

miscellaneous words, names, and phrases without a clear pattern

oai_token-act-pair · gpt-3.5-turbo

instances of the character "L" with varying context and placement within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pitfalls

-0.71

 retirees

-0.69

 policymakers

-0.68

 partnerships

-0.68

 relevance

-0.66

 consequential

-0.65

 advantages

-0.65

 satell

-0.64

utterstock

-0.64

 advertisers

-0.64

POSITIVE LOGITS

ï¸ı

1.27

âĶĢâĶĢ

1.12

âĶĢâĶĢâĶĢâĶĢ

1.04

âĻ

0.96

âĶĢ

0.92

xxx

0.90

âĹ

0.90

REDACTED

0.89

dro

0.86

ï¸

0.83

Activations Density 0.500%

miscellaneous words, names, and phrases without a clear pattern

instances of the character "L" with varying context and placement within the text

No Comments

No Known Activations